Access to healthcare in the USA is a major concern as there are many factors that contribute to gaps in access to care. The lack of healthcare providers in rural and low-income areas, the high cost of insurance and medical services, and limited insurance coverage options are just a few of the issues that contribute to this problem. A solution to this problem would be to develop a system that identifies the geographical presence and distribution of healthcare providers based on various input factors, such as distance from current location, specialty or provider type, insurance types accepted, availability, ratings, certifications, and specialties. This system could be accessible through a website or mobile application, making it easy for people to search for and find the right provider for their needs. This would help ensure that everyone has access to quality healthcare, regardless of where they live or their financial situation. The article "Top Challenges Impacting Patient Access to Healthcare" discusses the various obstacles that individuals face in accessing quality healthcare. Some of the challenges discussed include lack of insurance coverage, limited access to providers in certain areas, high cost of care, and complex healthcare systems that are difficult to navigate. These challenges result in many individuals being unable to access the care they need, leading to poor health outcomes and increased costs in the long run. The article highlights the importance of addressing these challenges in order to improve access to healthcare and ensure that everyone has the opportunity to receive quality care.

As a result, we felt motivated to tackle this issue and develop a ML algorithm that would collect the longitude and latitude of the patient in need, the amount of the money they can spend and if they are in a traumatic situation to be able to find a nearby hospital.

Tools used

We used a variety of Python packages for data cleaning, manipulation, and analysis within Google Colab. Pandas was the main package used to wrangle raw data and delete unnecessary columns and eventually merge all the data into a master dataframe. The “nltk” package was used to conduct natural language processing (NLP) to analyze patient symptoms. This analysis was then used to assess the need of the patient for a high or low trauma center to filter throughout the hospital data. Streamlit was used for web app deployment and creation. The app was designed such that the user can input metrics such as maximum cost and symptoms and then run. The app would then use that information to filter out the best hospitals and use a ML model to provide the top recommended hospitals.